Matches in SemOpenAlex for { <https://semopenalex.org/work/W4289534963> ?p ?o ?g. }
Showing items 1 to 57 of
57
with 100 items per page.
- W4289534963 abstract "Dynamic graph neural networks have been widely used in modeling and representation learning of graph structure data. Current dynamic representation learning focuses on either discrete learning which results in temporal information loss or continuous learning that involves heavy computation. In this work, we proposed a novel dynamic graph neural network, Sparse-Dyn. It adaptively encodes temporal information into a sequence of patches with an equal amount of temporal-topological structure. Therefore, while avoiding the use of snapshots which causes information loss, it also achieves a finer time granularity, which is close to what continuous networks could provide. In addition, we also designed a lightweight module, Sparse Temporal Transformer, to compute node representations through both structural neighborhoods and temporal dynamics. Since the fully-connected attention conjunction is simplified, the computation cost is far lower than the current state-of-the-arts. Link prediction experiments are conducted on both continuous and discrete graph datasets. Through comparing with several state-of-the-art graph embedding baselines, the experimental results demonstrate that Sparse-Dyn has a faster inference speed while having competitive performance." @default.
- W4289534963 created "2022-08-03" @default.
- W4289534963 creator A5000647003 @default.
- W4289534963 creator A5028296024 @default.
- W4289534963 date "2022-01-04" @default.
- W4289534963 modified "2023-10-16" @default.
- W4289534963 title "Sparse-Dyn: Sparse Dynamic Graph Multi-representation Learning via Event-based Sparse Temporal Attention Network" @default.
- W4289534963 doi "https://doi.org/10.48550/arxiv.2201.01384" @default.
- W4289534963 hasPublicationYear "2022" @default.
- W4289534963 type Work @default.
- W4289534963 citedByCount "0" @default.
- W4289534963 crossrefType "posted-content" @default.
- W4289534963 hasAuthorship W4289534963A5000647003 @default.
- W4289534963 hasAuthorship W4289534963A5028296024 @default.
- W4289534963 hasBestOaLocation W42895349631 @default.
- W4289534963 hasConcept C111919701 @default.
- W4289534963 hasConcept C11413529 @default.
- W4289534963 hasConcept C124066611 @default.
- W4289534963 hasConcept C132525143 @default.
- W4289534963 hasConcept C154945302 @default.
- W4289534963 hasConcept C177774035 @default.
- W4289534963 hasConcept C2776214188 @default.
- W4289534963 hasConcept C41008148 @default.
- W4289534963 hasConcept C41608201 @default.
- W4289534963 hasConcept C45374587 @default.
- W4289534963 hasConcept C59404180 @default.
- W4289534963 hasConcept C75564084 @default.
- W4289534963 hasConcept C80444323 @default.
- W4289534963 hasConceptScore W4289534963C111919701 @default.
- W4289534963 hasConceptScore W4289534963C11413529 @default.
- W4289534963 hasConceptScore W4289534963C124066611 @default.
- W4289534963 hasConceptScore W4289534963C132525143 @default.
- W4289534963 hasConceptScore W4289534963C154945302 @default.
- W4289534963 hasConceptScore W4289534963C177774035 @default.
- W4289534963 hasConceptScore W4289534963C2776214188 @default.
- W4289534963 hasConceptScore W4289534963C41008148 @default.
- W4289534963 hasConceptScore W4289534963C41608201 @default.
- W4289534963 hasConceptScore W4289534963C45374587 @default.
- W4289534963 hasConceptScore W4289534963C59404180 @default.
- W4289534963 hasConceptScore W4289534963C75564084 @default.
- W4289534963 hasConceptScore W4289534963C80444323 @default.
- W4289534963 hasLocation W42895349631 @default.
- W4289534963 hasOpenAccess W4289534963 @default.
- W4289534963 hasPrimaryLocation W42895349631 @default.
- W4289534963 hasRelatedWork W10765648 @default.
- W4289534963 hasRelatedWork W12563130 @default.
- W4289534963 hasRelatedWork W12987287 @default.
- W4289534963 hasRelatedWork W14632104 @default.
- W4289534963 hasRelatedWork W2135213 @default.
- W4289534963 hasRelatedWork W2177595 @default.
- W4289534963 hasRelatedWork W3594516 @default.
- W4289534963 hasRelatedWork W4136762 @default.
- W4289534963 hasRelatedWork W5374421 @default.
- W4289534963 hasRelatedWork W6426808 @default.
- W4289534963 isParatext "false" @default.
- W4289534963 isRetracted "false" @default.
- W4289534963 workType "article" @default.